© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38391
    Prev
    Next
    INDEX
    Explanations

    gravity or scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    the
    0.98
    not
    0.87
    テナンス
    0.71
    0
    0.70
     όχι
    0.70
    ním
    0.70
     hoofd
    0.69
    nutí
    0.68
    OOL
    0.68
    OVA
    0.67
    POSITIVE LOGITS
    一緒に
    0.78
    ville
    0.73
    ש
    0.73
    ח
    0.73
    als
    0.71
    vast
    0.70
    ho
    0.68
     to
    0.67
    zi
    0.67
    ي
    0.67
    Activations Density 0.103%

    No Known Activations